Latest News

Alibaba’s self-driving robots deliver over one million orders

Alibaba DAMO Academy, the global research initiative set up by Alibaba Group, today announced that the last-mile logistics vehicle “Xiaomanlv”, developed by its autonomous driving lab (“lab”), has delivered over one million shipment orders as of September 2021. Xiaomanlv achieved this milestone within one year of its launch, serving over 160 urban communities and school campuses across 52 cities in mainland China. Collectively, they have delivered packages to more than 200,000 consumers.

The lab also announced plans to increase the fleet of Xiaomanlv to 10,000 over the coming three years, boosting delivery capacity to one million packages per day.

Alibaba has been exploring autonomous driving technology since 2015 to address the last-mile delivery challenges associated with the e-commerce economy. By leveraging its cloud-based intelligent simulation testing platform, which is able to create up to 10,000 virtual scenarios – including extreme weather and ultra-weak night visibility scenarios – for testing the robot’s algorithm. Xiaomanlv can manage without human intervention 99.9999% of the time, despite the challenge that it needs to identify over 40 million obstacles during a typical day’s work.

“One important breakthrough is our ability to use advanced algorithms to achieve a low-cost mass deployment of our self-driving vehicles across communities and campuses,” said Gang Wang, Head of Autonomous Driving Lab, Alibaba DAMO Academy.

“Through our proprietary multi-sensor fusion solution and cutting-edge machine learning platform AutoDrive, we are able to achieve the L4 level of autonomous driving without leaning on expensive, high-definition sensors to navigate. This helps us significantly cut down our hardware costs. As a result, the overall per unit cost of production and operation is just about one third of the industry average,” added Gang. On a scale of Level 1 to 5 in autonomous driving, Level 4 means a high degree of automation.

Currently there are over 200 Xiaomanlv operating in 22 provinces in China, and Alibaba plans to deploy a total of 1,000 vehicles by March next year. Each robot can deliver around 50 packages at a time and as many as 500 boxes per day, covering 100 kilometres on a single charge.

Wang also revealed that the lab has been working with Cainiao, the logistics arm of Alibaba Group, on driverless delivery trucks, in view of enabling autonomous deliveries in faster speed scenarios and over longer distances. He expects the trucks to be running on public roads in various cities with three years.

The lab is also developing other products equipped with autonomous driving capabilities, including inspection robots in electricity power plants, which are expected to be put into use in the near future.